Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents

TL;DR

Psychlab is a flexible simulation environment within DeepMind Lab that enables classical psychological experiments with both humans and AI, leading to new insights and improvements in deep reinforcement learning agents.

Contribution

Introduction of Psychlab, a versatile platform for psychological experiments with AI, and a study revealing how visual stimulus size affects learning in deep RL agents, leading to performance improvements.

Findings

UNREAL learns faster with larger stimuli.

Foveal vision model improves UNREAL performance.

Psychlab facilitates future cognitive science and RL research.

Abstract

Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016). Psychlab enables implementations of classical laboratory psychological experiments so that they work with both human and artificial agents. Psychlab has a simple and flexible API that enables users to easily create their own tasks. As examples, we are releasing Psychlab implementations of several classical experimental paradigms including visual search, change detection, random dot motion discrimination, and multiple object tracking. We also contribute a study of the visual psychophysics of a specific state-of-the-art deep reinforcement learning agent: UNREAL (Jaderberg et al. 2016). This study leads to the surprising conclusion that UNREAL learns more quickly about larger target stimuli than it does about smaller stimuli. In turn, this insight motivates a specific improvement in the form of a simple model of foveal vision that turns out to significantly boost UNREAL's performance, both on Psychlab tasks, and on standard DeepMind Lab tasks. By open-sourcing Psychlab we hope to facilitate a range of future such studies that simultaneously advance deep reinforcement learning and improve its links with cognitive science.